Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/puppylpg/puppylpg.github.io/summarize-articlenpx skills add puppylpg/puppylpg.github.io --skill summarize-articlegit clone --depth 1 https://github.com/puppylpg/puppylpg.github.ioWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/puppylpg/puppylpg.github.io/summarize-article)<a href="https://agentmods.dev/skills/puppylpg/puppylpg.github.io/summarize-article"><img src="https://agentmods.dev/badge/skills/puppylpg/puppylpg.github.io/summarize-article.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00108 | $0.02231 |
| Opus 5 | $0.00054 | $0.01115 |
| Sonnet 5 | $0.00022 | $0.00446 |
| Haiku 4.5 | $0.00011 | $0.00223 |
Grade A, and why
summarize-article scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
86% identical to chat_with_agent — 189 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
将来源文章重写为博客文章
核心原则
来源文章是素材和证据,不是必须照抄的文章骨架。
最终文章应独立成立。读者不需要先读原文,也不应看到“作者先说了什么、接着又说了什么”的流水账。先理解原文,再按照中文读者理解主题所需的知识顺序重新组织。
禁止:
- 按原文章节逐节缩写,形成目录级复述;
- 把原文中的问题逐条改成 FAQ;
- 频繁使用“原文提到”“作者接着说”等转述句;
- 把后续追问或纠错直接追加成对不可见问题的答复;
- 为了简短而删掉关键证据、推理步骤和贯穿例子。
工作流程
1. 完整获取来源
- URL:使用当前可用的网页工具获取正文;内容为空、被截断或依赖动态渲染时,改用浏览器自动化。
- 微信公众号:优先使用浏览器自动化,避免在常规抓取失败上反复消耗时间。
- 本地文件或用户提供的正文:直接读取。
记录原文标题、来源链接、作者和发布日期(能确认时)。若关键内容无法获取,先说明缺失范围,不根据摘要或搜索片段臆造全文。
涉及可能变化的事实、专业争议或高风险结论时,使用一手来源核实;明确区分原作者观点、可验证事实和自己的推断。
2. 根据材料规模选择执行方式
短文章或结构清晰的单一来源由主 agent 直接完成,避免为了分工增加交接成本。
出现以下情况时,可以使用子 agent:
- 原文很长,完整抓取、材料分析和成文会占用大量上下文;
- 需要同时处理多篇来源、多个附件或大量图表;
- 网页抓取、事实核验和正文写作可以拆成彼此独立的任务;
- 用户明确要求并行处理或使用子 agent。
“很长”不设固定字数,以材料是否明显挤压后续分析和写作空间为准。使用子 agent 是上下文管理和并行处理手段,不是每次总结文章都必须经过的仪式。
决定委派时:
- 主 agent 先明确文章目标、来源范围、目标目录和子任务边界;
- 让子 agent 承担完整抓取与材料图谱,或在指定路径生成初稿;同一文件同时只由一个 agent 编辑;
- 使用前完整读取
assets/PROMPT.md,按实际任务选择“材料整理”或“完整初稿”模式; - 主 agent 必须检查来源获取是否完整、通读初稿、复核关键事实,并负责重组叙事、冷读验收、预览和发布,不能只接收路径后直接发布。
3. 提炼主题和知识依赖
阅读完整来源后确定:
- 原文试图解释的核心对象或解决的问题;
- 零上下文读者需要先知道的背景和概念;
- 主要论点、证据、机制、例子和结论之间的关系;
- 原文隐含的假设、适用边界和遗漏;
- 哪个具体例子最适合贯穿全文;
- 最终文章范围是否需要收缩或扩展。
删除重复论述、修辞性铺垫和不影响结论的细节,但保留支撑判断所必需的证据。
4. 重新设计叙事
不要默认沿用原文目录。根据知识依赖选择一条主线,通常按以下顺序推进:
核心思想:一两句话给出最值得记住的判断
→ 来源与问题背景
→ 具体场景或直觉例子
→ 必要概念和组件关系
→ 机制、流程或论证
→ 结果与工程含义
→ 局限、适用边界和自然推出的判断
写正文前先确定每个 H2 的核心一句话,并检查它为什么出现在这里、依赖哪些前文、为下一节建立什么基础。
原文结构清晰时可以部分沿用;结构不适合中文科普阅读时必须重组。用户后续补充的信息也要拆回相应概念的位置,不得变成文章末尾的问答补丁。
5. 写成自然的中文文章
- Frontmatter 后立即写固定的“核心”章节,不在它前面放来源、背景、题记或其他正文。
- “核心”的第一段只用一两句话写出全文最值得记住的思想。让没有时间继续阅读的人只看这一段也能获得文章最重要的判断;不要写成章节目录、内容预告或“本文将介绍”。
- 可以使用准确、有概括力的抽象名词,但零上下文读者未必能直接理解的名词首次出现时,必须紧跟中文括号,用具体、白话的动作或关系解释含义,例如“控制点上移(人不再亲自执行每一步,而是转去设计目标、环境和规则)”。括号内不要只换一个近义词,也不要连续堆叠多个未经解释的概念。
- 在“核心”之后使用有意义的 Markdown 链接注明原始来源,再从背景和问题张力展开完整论证。
- 英文内容按中文表达习惯重述:拆分长句、主动表达、重组从句,不逐字硬翻。
- 没有统一译法的专业术语首次出现时标注英文原词,后续不重复。
- 先建立直觉,再引入术语、公式或实现细节。
- 公式使用本站兼容的行内
$...$和块级$$...$$,首次出现时解释符号与维度。 - 流程、层级、时序、架构和状态关系优先使用合适的 Mermaid 图;避免装饰性图表。
- 以转述和分析为主,只保留必要的短引文,避免大段复制原文。
- 在相应论点或边界第一次需要时加入必要的分析和纠偏,但不能用分散评论代替固定的“评价”章节。
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 159 lines · 108 tokens per session scan A 941d31e12a94
summarize-article is a skill published in the GitHub repository puppylpg/puppylpg.github.io (2 stars, last pushed 9d ago), licensed MIT. It adds 108 tokens to every session and 2,231 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to chat_with_agent, differing in 189 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…